{ "architectures": [ "Qwen3MoeForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 2, "decoder_sparse_step": 1, "dtype": "bfloat16", "eos_token_id": 1, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_only_layers": [], "model_type": "qwen3_moe", "moe_intermediate_size": 1408, "norm_topk_prob": true, "num_attention_heads": 32, "num_experts_per_tok": 8, "num_hidden_layers": 36, "num_key_value_heads": 8, "num_local_experts": 128, "output_router_logits": false, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 1000000.0, "rope_type": "default" }, "router_aux_loss_coef": 0.001, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "5.8.0", "use_cache": false, "use_sliding_window": false, "vocab_size": 262144 }